Using an anomaly detection approach for the segmentation of colorectal cancer tumors in whole slide images

Qiangqiang Gu; Chady Meroueh; Jacob Levernier; Trynda Kroneman; Thomas Flotte; Steven Hart

doi:10.1016/j.jpi.2023.100336

Using an anomaly detection approach for the segmentation of colorectal cancer tumors in whole slide images

J Pathol Inform. 2023 Sep 22:14:100336. doi: 10.1016/j.jpi.2023.100336. eCollection 2023.

Authors

Qiangqiang Gu¹, Chady Meroueh¹, Jacob Levernier¹, Trynda Kroneman¹, Thomas Flotte¹, Steven Hart^{1

2}

Affiliations

¹ Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN 55901, United States.
² Department of Quantitative Health Science, Mayo Clinic, Rochester, MN 55901, United States.

Abstract

Colorectal cancer (CRC) is the second most commonly diagnosed cancer in the United States. Genetic testing is critical in assisting in the early detection of CRC and selection of individualized treatment plans, which have shown to improve the survival rate of CRC patients. The tissue slide review (TSR), a tumor tissue macro-dissection procedure, is a required pre-analytical step to perform genetic testing. Due to the subjective nature of the process, major discrepancies in CRC diagnostics by pathologists are reported, and metrics for quality are often only qualitative. Progressive context encoder anomaly detection (P-CEAD) is an anomaly detection approach to detect tumor tissue from whole slide images (WSIs), since tumor tissue is by its nature, an anomaly. P-CEAD-based CRC tumor segmentation achieves a 71% 26% sensitivity, 92% 7% specificity, and 63% 23% F1 score. The proposed approach provides an automated CRC tumor segmentation pipeline with a quantitatively reproducible quality compared with the conventional manual tumor segmentation procedure.

Keywords: Anomaly detection; Colorectal cancer; Tissue slide review.